mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-25 22:40:51 +07:00
1cedee13d2
In addition to already existing BPF hooks for sys_bind and sys_connect, the patch provides new hooks for sys_sendmsg. It leverages existing BPF program type `BPF_PROG_TYPE_CGROUP_SOCK_ADDR` that provides access to socket itlself (properties like family, type, protocol) and user-passed `struct sockaddr *` so that BPF program can override destination IP and port for system calls such as sendto(2) or sendmsg(2) and/or assign source IP to the socket. The hooks are implemented as two new attach types: `BPF_CGROUP_UDP4_SENDMSG` and `BPF_CGROUP_UDP6_SENDMSG` for UDPv4 and UDPv6 correspondingly. UDPv4 and UDPv6 separate attach types for same reason as sys_bind and sys_connect hooks, i.e. to prevent reading from / writing to e.g. user_ip6 fields when user passes sockaddr_in since it'd be out-of-bound. The difference with already existing hooks is sys_sendmsg are implemented only for unconnected UDP. For TCP it doesn't make sense to change user-provided `struct sockaddr *` at sendto(2)/sendmsg(2) time since socket either was already connected and has source/destination set or wasn't connected and call to sendto(2)/sendmsg(2) would lead to ENOTCONN anyway. Connected UDP is already handled by sys_connect hooks that can override source/destination at connect time and use fast-path later, i.e. these hooks don't affect UDP fast-path. Rewriting source IP is implemented differently than that in sys_connect hooks. When sys_sendmsg is used with unconnected UDP it doesn't work to just bind socket to desired local IP address since source IP can be set on per-packet basis by using ancillary data (cmsg(3)). So no matter if socket is bound or not, source IP has to be rewritten on every call to sys_sendmsg. To do so two new fields are added to UAPI `struct bpf_sock_addr`; * `msg_src_ip4` to set source IPv4 for UDPv4; * `msg_src_ip6` to set source IPv6 for UDPv6. Signed-off-by: Andrey Ignatov <rdna@fb.com> Acked-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
218 lines
7.5 KiB
C
218 lines
7.5 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _BPF_CGROUP_H
|
|
#define _BPF_CGROUP_H
|
|
|
|
#include <linux/jump_label.h>
|
|
#include <uapi/linux/bpf.h>
|
|
|
|
struct sock;
|
|
struct sockaddr;
|
|
struct cgroup;
|
|
struct sk_buff;
|
|
struct bpf_sock_ops_kern;
|
|
|
|
#ifdef CONFIG_CGROUP_BPF
|
|
|
|
extern struct static_key_false cgroup_bpf_enabled_key;
|
|
#define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key)
|
|
|
|
struct bpf_prog_list {
|
|
struct list_head node;
|
|
struct bpf_prog *prog;
|
|
};
|
|
|
|
struct bpf_prog_array;
|
|
|
|
struct cgroup_bpf {
|
|
/* array of effective progs in this cgroup */
|
|
struct bpf_prog_array __rcu *effective[MAX_BPF_ATTACH_TYPE];
|
|
|
|
/* attached progs to this cgroup and attach flags
|
|
* when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will
|
|
* have either zero or one element
|
|
* when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS
|
|
*/
|
|
struct list_head progs[MAX_BPF_ATTACH_TYPE];
|
|
u32 flags[MAX_BPF_ATTACH_TYPE];
|
|
|
|
/* temp storage for effective prog array used by prog_attach/detach */
|
|
struct bpf_prog_array __rcu *inactive;
|
|
};
|
|
|
|
void cgroup_bpf_put(struct cgroup *cgrp);
|
|
int cgroup_bpf_inherit(struct cgroup *cgrp);
|
|
|
|
int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
|
|
enum bpf_attach_type type, u32 flags);
|
|
int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
|
|
enum bpf_attach_type type, u32 flags);
|
|
int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
|
|
union bpf_attr __user *uattr);
|
|
|
|
/* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */
|
|
int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
|
|
enum bpf_attach_type type, u32 flags);
|
|
int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
|
|
enum bpf_attach_type type, u32 flags);
|
|
int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
|
|
union bpf_attr __user *uattr);
|
|
|
|
int __cgroup_bpf_run_filter_skb(struct sock *sk,
|
|
struct sk_buff *skb,
|
|
enum bpf_attach_type type);
|
|
|
|
int __cgroup_bpf_run_filter_sk(struct sock *sk,
|
|
enum bpf_attach_type type);
|
|
|
|
int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
|
|
struct sockaddr *uaddr,
|
|
enum bpf_attach_type type,
|
|
void *t_ctx);
|
|
|
|
int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
|
|
struct bpf_sock_ops_kern *sock_ops,
|
|
enum bpf_attach_type type);
|
|
|
|
int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
|
|
short access, enum bpf_attach_type type);
|
|
|
|
/* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */
|
|
#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \
|
|
({ \
|
|
int __ret = 0; \
|
|
if (cgroup_bpf_enabled) \
|
|
__ret = __cgroup_bpf_run_filter_skb(sk, skb, \
|
|
BPF_CGROUP_INET_INGRESS); \
|
|
\
|
|
__ret; \
|
|
})
|
|
|
|
#define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb) \
|
|
({ \
|
|
int __ret = 0; \
|
|
if (cgroup_bpf_enabled && sk && sk == skb->sk) { \
|
|
typeof(sk) __sk = sk_to_full_sk(sk); \
|
|
if (sk_fullsock(__sk)) \
|
|
__ret = __cgroup_bpf_run_filter_skb(__sk, skb, \
|
|
BPF_CGROUP_INET_EGRESS); \
|
|
} \
|
|
__ret; \
|
|
})
|
|
|
|
#define BPF_CGROUP_RUN_SK_PROG(sk, type) \
|
|
({ \
|
|
int __ret = 0; \
|
|
if (cgroup_bpf_enabled) { \
|
|
__ret = __cgroup_bpf_run_filter_sk(sk, type); \
|
|
} \
|
|
__ret; \
|
|
})
|
|
|
|
#define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) \
|
|
BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET_SOCK_CREATE)
|
|
|
|
#define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) \
|
|
BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET4_POST_BIND)
|
|
|
|
#define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) \
|
|
BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET6_POST_BIND)
|
|
|
|
#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, type) \
|
|
({ \
|
|
int __ret = 0; \
|
|
if (cgroup_bpf_enabled) \
|
|
__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \
|
|
NULL); \
|
|
__ret; \
|
|
})
|
|
|
|
#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) \
|
|
({ \
|
|
int __ret = 0; \
|
|
if (cgroup_bpf_enabled) { \
|
|
lock_sock(sk); \
|
|
__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \
|
|
t_ctx); \
|
|
release_sock(sk); \
|
|
} \
|
|
__ret; \
|
|
})
|
|
|
|
#define BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr) \
|
|
BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET4_BIND)
|
|
|
|
#define BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr) \
|
|
BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET6_BIND)
|
|
|
|
#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (cgroup_bpf_enabled && \
|
|
sk->sk_prot->pre_connect)
|
|
|
|
#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) \
|
|
BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET4_CONNECT)
|
|
|
|
#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) \
|
|
BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET6_CONNECT)
|
|
|
|
#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) \
|
|
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_CONNECT, NULL)
|
|
|
|
#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) \
|
|
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_CONNECT, NULL)
|
|
|
|
#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) \
|
|
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP4_SENDMSG, t_ctx)
|
|
|
|
#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) \
|
|
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_SENDMSG, t_ctx)
|
|
|
|
#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \
|
|
({ \
|
|
int __ret = 0; \
|
|
if (cgroup_bpf_enabled && (sock_ops)->sk) { \
|
|
typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk); \
|
|
if (__sk && sk_fullsock(__sk)) \
|
|
__ret = __cgroup_bpf_run_filter_sock_ops(__sk, \
|
|
sock_ops, \
|
|
BPF_CGROUP_SOCK_OPS); \
|
|
} \
|
|
__ret; \
|
|
})
|
|
|
|
#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access) \
|
|
({ \
|
|
int __ret = 0; \
|
|
if (cgroup_bpf_enabled) \
|
|
__ret = __cgroup_bpf_check_dev_permission(type, major, minor, \
|
|
access, \
|
|
BPF_CGROUP_DEVICE); \
|
|
\
|
|
__ret; \
|
|
})
|
|
#else
|
|
|
|
struct cgroup_bpf {};
|
|
static inline void cgroup_bpf_put(struct cgroup *cgrp) {}
|
|
static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
|
|
|
|
#define cgroup_bpf_enabled (0)
|
|
#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
|
|
#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
|
|
#define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
|
|
#define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
|
|
#define BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr) ({ 0; })
|
|
#define BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr) ({ 0; })
|
|
#define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; })
|
|
#define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; })
|
|
#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 0; })
|
|
#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) ({ 0; })
|
|
#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) ({ 0; })
|
|
#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) ({ 0; })
|
|
#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; })
|
|
#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; })
|
|
#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
|
|
#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
|
|
|
|
#endif /* CONFIG_CGROUP_BPF */
|
|
|
|
#endif /* _BPF_CGROUP_H */
|